Authors: Ahmed Elrashidy, James Della-Giustina, Jia-An Yan

Published on: November 02, 2023

Impact Score: 8.38

Arxiv code: Arxiv:2311.00939

Summary

• What is new: Using Graph Neural Networks to identify promising 2D magnetic materials, significantly speeding up the discovery process compared to traditional methods.
• Why this is important: The slow pace of discovering new 2D magnetic materials for spintronics.
• What the research proposes: Employing GNNs to efficiently filter through potential 2D magnetic materials, identifying 167 new candidates.
• Results: Achieved 93% accuracy in predicting magnetic properties and identified 167 new magnetic monolayers from 11,100 candidates.

Technical Details

Technological frameworks used: Graph Neural Networks (GNNs), Crystal Diffusion Variational Auto Encoder (CDVAE), Atomistic Line Graph Neural Networks (ALIGNN)

Models used: CDVAE, two ALIGNN

Data used: Materials Project database, Computational 2D materials database (C2DB)

Potential Impact

Spintronics, materials science companies, and industries relying on advanced magnetic materials (e.g., data storage, memory devices).

Want to implement this idea in a business?

We have generated a startup concept here: GrapheneXplore.